An Intelligent System for the Heatsink Design
Via two-stage back-propagation neural network (BNN) learning algorithm, this paper establishes the relationship between different heatsink design parameters and performance evaluation, and induces 5 corresponding performance outputs from 6 different heatsink design and operating condition parameters (inlet airflow velocity, heatsink length or width, fin thickness, fin gap, fin height and heatsink base height) by using Computation Fluid Dynamics (CFD). After two stages well-trained, the BNN model with error compensator is able to accurate estimate the output values under different heatsink design and operation conditions.
KeywordsError Compensator Airflow Velocity Computation Fluid Dynamics Chip Package Operating Condition Parameter
Unable to display preview. Download preview PDF.
- 1.Kraus, A., Bar-Cohen, A.: Thermal Analysis and Control of Electronic Equipment. Hemisphere Publishing Corp. (1983)Google Scholar
- 3.Bar-Cohen, A.: Thermal Management of Air- and Liquid- Cooled Multichip Modules. IEEE Transactions CPMT 10(2), 159–175 (1988)Google Scholar
- 4.Bar-Cohen, A.: Thermal Packaging for the 21st Century. Invited Talk. In: 5th Therminic – International Workshop Thermal Investigations of ICs and System, Rome, Italy, October 3-6 (1999)Google Scholar
- 5.Bar-Cohen, A., Krueger, W.B.: Thermal Characterization of Chip Packages: Evolutionary Development of Compact Models. IEEE Transactions CPMT - Part A (1997)Google Scholar
- 6.Patanker, S.V.: Numerical Heat Transfer and Fluid Flow. Hemisphere Publishing Co. (1980)Google Scholar